Leveraging Machine Learning for Advanced Passive Sonar Tracking
SBIR Opportunity Analysis
The U.S. Navy, through the Department of Defense SBIR program, is seeking machine learning approaches to improve passive sonar tracking, classification, fusion, and localization for anti-submarine warfare systems. The work calls for advanced automation that can detect, locate, classify, and correlate contacts across multiple sonar sensors and display surfaces, with Phase I focused on algorithm development and Phase II on implementation in a simulated environment using government-provided Navy sonar data. Key performance areas include hold time ratio, time to track, correct classification, false alerts, correct association, and localization uncertainty, and the effort may become classified in Phase II. The contractor must be U.S.-owned and operated, comply with export control restrictions, and be able to obtain and maintain secret-level facility and personnel clearances. Proposals are due June 3, 2026 at 4:00 PM UTC.